Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography (한국측량학회지)

Korean Society of Surveying, Geodesy, Photogrammetry and Cartography (한국측량학회)
권호 표지
DOI QR코드

DOI QR Code

Spatiotemporal Resolution Enhancement of PM10 Concentration Data Using Satellite Image and Sensor Data in Deep Learning

위성 영상과 관측 센서 데이터를 이용한 PM10농도 데이터의 시공간 해상도 향상 딥러닝 모델 설계

  • Baek, Chang-Sun (Dept. of Geoinformation Engineering, Sejong University) ;
  • Yom, Jae-Hong (Dept. of Environment, Energy & Geoinformatics, Sejong University)
  • Received : 2019.11.21
  • Accepted : 2019.12.26
  • Published : 2019.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

PM10 concentration is a spatiotemporal phenomenta and capturing data for such continuous phenomena is a difficult task. This study designed a model that enhances spatiotemporal resolution of PM10 concentration levels using satellite imagery, atmospheric and meteorological sensor data, and multiple deep learning models. The designed deep learning model was trained using input data whose factors may affect concentration of PM10 such as meteorological conditions and land-use. Using this model, PM10 images having 15 minute temporal resolution and 30m×30m spatial resolution were produced with only atmospheric and meteorological data.

PM10 농도는 시간 및 공간 의존성을 동시에 가지는 시공간 데이터이지만 현실적으로 연속적인 시공간 데이터를 획득하는 것은 쉬운 일이 아니다. 본 연구에서는 위성영상과 대기질 및 기상 관측 센서 데이터를 복합적인 딥러닝 모델에 적용하여 시공간 해상도를 향상시키는 모델을 설계하였다. 설계된 딥러닝 모델은 기상, 토지 이용 등 PM10 농도에 영향을 줄 수 있는 인자를 이용하여 학습하였으며, 대기질 및 기상 관측 데이터만을 이용하여 15분 단위의 30m×30m의 공간해상도를 PM10 영상을 생성하였다.

Keywords

Acknowledgement

Supported by : 한국연구재단

이 연구는 한국연구재단 이공분야기초연구사업(NRF-2018R1D1A1B07043821)의 지원으로 수행되었습니다.

References

  1. Abderrahim, H., Chellali, M.R., and Hamou, A. (2016), Forecasting PM 10 in Algiers: Efficacy of multilayer perceptron networks, Environmental Science and Pollution Research, Vol. 23, No. 2, pp. 1634-1641. https://doi.org/10.1007/s11356-015-5406-6
  2. Hochreiter, S. and Jurgen S. (1997), Long short-term memory, Neural Computation, Vol. 9, No. 8, pp. 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  3. Hooyberghs, J., Mensink, C., Dumont, G., Fierens, F., and Brasseur, O. (2005), A neural network forecast for daily average PM10 concentrations in Belgium, Atmospheric Environment, Vol. 39, No. 18, pp. 3279-3289. https://doi.org/10.1016/j.atmosenv.2005.01.050
  4. Kingma, D.P. and Welling, M. (2013), Auto-encoding variational bayes, 2nd Proceedings of the International Conference on Learning Representations, ICLR, 2-4 May, Scottsdale, Arizona, USA
  5. Kingma, D.P., Mohamed, S., Rezende, D.J., and Welling, M. (2014), Semi-supervised learning with deep generative models, In Advances in Neural Information Processing Systems, pp. 3581-3589.
  6. Kloog, I., Koutrakis, P., Coull, B.A., Lee, H.J., and Schwartz, J. (2011), Assessing temporally and spatially resolved PM2.5 exposures for epidemiological studies using satellite aerosol optical depth measurements, Atmospheric Environment, Vol. 45, No. 35, pp. 6267-6275. https://doi.org/10.1016/j.atmosenv.2011.08.066
  7. Krawczyk, B. (2016), Learning from imbalanced data: open challenges and future directions, Progress in Artificial Intelligence, Vol. 5, No. 4, pp. 221-232. https://doi.org/10.1007/s13748-016-0094-0
  8. Le, V.D. (2019), Spatiotemporal Deep Learning Model for Citywide Air Pollution Interpolation and Prediction, Master's thesis, Seoul National University, Seoul, Korea, 52p.
  9. Saleh, S.A.H. and Hasan, G. (2014), Estimation of PM10 concentration using ground measurements and Landsat 8 OLI satellite image, Journal of Geophysics and Remote Sensing, Vol. 3 No. 2, pp. 2169-0049.
  10. Saraswat, I., Mishra, R.K., and Kumar, A. (2017), Estimation of PM10 concentration from Landsat 8 OLI satellite imagery over Delhi, India, Remote Sensing Applications: Society and Environment, Vol. 8, pp. 251-257. https://doi.org/10.1016/j.rsase.2017.10.006
  11. Shahraiyni, H.T. and Sodoudi, S. (2016), Statistical modeling approaches for PM10 prediction in urban areas: A review of 21st-century studies, Atmosphere, Vol. 7, No. 2, 15p. https://doi.org/10.3390/atmos7020015
  12. Wen, C., Liu, S., Yao, X., Peng, L., Li, X., Hu, Y., and Chi, T. (2019), A novel spatiotemporal convolutional long short-term neural network for air pollution prediction, Science of The Total Environment, Vol. 654, pp. 1091-1099. https://doi.org/10.1016/j.scitotenv.2018.11.086
  13. Yao, L., Lu, N., and Jiang, S. (2012), Artificial neural network (ANN) for multi-source PM2.5 estimation using surface, MODIS, and Fig.rological data, International Conference on Biomedical Engineering and Biotechnology, IEEE, 28-30 May, Macau, China, pp. 1228-1231.
  14. Zhou, Y., Chang, F.J., Chang, L.C., Kao, I.F., and Wang, Y.S. (2019), Explore a deep learning multi-output neural network for regional multi-step-ahead air quality forecasts, Journal of Cleaner Production, Vol. 209, pp. 134-145. https://doi.org/10.1016/j.jclepro.2018.10.243